A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction

Traffic flow prediction, crucial for intelligent transportation systems, has seen advancements with graph neural networks (GNNs), yet existing methods often fail to distinguish between the importance of different intersections. These methods usually model all intersections uniformly, overlooking sig...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangting Liu, Chengyuan Qian, Xueyang Zhao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850032142966325248
author Xiangting Liu
Chengyuan Qian
Xueyang Zhao
author_facet Xiangting Liu
Chengyuan Qian
Xueyang Zhao
author_sort Xiangting Liu
collection DOAJ
description Traffic flow prediction, crucial for intelligent transportation systems, has seen advancements with graph neural networks (GNNs), yet existing methods often fail to distinguish between the importance of different intersections. These methods usually model all intersections uniformly, overlooking significant differences in traffic flow characteristics and influence ranges between ordinary and important nodes. To tackle this, this study introduces a dynamic regional-aggregation-based heterogeneous graph neural network (DR-HGNN). This model categorizes intersections into two types—ordinary and important—to apply tailored feature aggregation strategies. Ordinary intersections aggregate features based on local neighborhood information, whereas important intersections utilize deeper neighborhood diffusion and multi-hop dependencies to capture broader traffic influences. The DR-HGNN model also employs a dynamic graph structure to reflect temporal changes in traffic flows, alongside an attention mechanism for adaptive regional feature aggregation, enhancing the identification of critical traffic nodes. Demonstrating its efficacy, the DR-HGNN achieved 19.2% and 15.4% improvements in the RMSE over 50 min predictions in the METR-LA and PEMS-BAY datasets, respectively, offering a more precise prediction method for traffic management.
format Article
id doaj-art-e17971687db7454fb4da787c4b4581f6
institution DOAJ
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-e17971687db7454fb4da787c4b4581f62025-08-20T02:58:44ZengMDPI AGMathematics2227-73902025-04-01139145810.3390/math13091458A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic PredictionXiangting Liu0Chengyuan Qian1Xueyang Zhao2School of International Education, Guangdong University of Technology, Guangzhou 511495, ChinaSchool of Mechanical and Energy Engineering, Tongji University, Shanghai 201804, ChinaDepartment of Mathematics and Physics, Harbin Institute of Petroleum, Harbin 150028, ChinaTraffic flow prediction, crucial for intelligent transportation systems, has seen advancements with graph neural networks (GNNs), yet existing methods often fail to distinguish between the importance of different intersections. These methods usually model all intersections uniformly, overlooking significant differences in traffic flow characteristics and influence ranges between ordinary and important nodes. To tackle this, this study introduces a dynamic regional-aggregation-based heterogeneous graph neural network (DR-HGNN). This model categorizes intersections into two types—ordinary and important—to apply tailored feature aggregation strategies. Ordinary intersections aggregate features based on local neighborhood information, whereas important intersections utilize deeper neighborhood diffusion and multi-hop dependencies to capture broader traffic influences. The DR-HGNN model also employs a dynamic graph structure to reflect temporal changes in traffic flows, alongside an attention mechanism for adaptive regional feature aggregation, enhancing the identification of critical traffic nodes. Demonstrating its efficacy, the DR-HGNN achieved 19.2% and 15.4% improvements in the RMSE over 50 min predictions in the METR-LA and PEMS-BAY datasets, respectively, offering a more precise prediction method for traffic management.https://www.mdpi.com/2227-7390/13/9/1458traffic flow predictiondynamic heterogeneous graph neural networkregional aggregationattention mechanismspatiotemporal dependencies
spellingShingle Xiangting Liu
Chengyuan Qian
Xueyang Zhao
A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
Mathematics
traffic flow prediction
dynamic heterogeneous graph neural network
regional aggregation
attention mechanism
spatiotemporal dependencies
title A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
title_full A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
title_fullStr A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
title_full_unstemmed A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
title_short A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
title_sort dynamic regional aggregation based heterogeneous graph neural network for traffic prediction
topic traffic flow prediction
dynamic heterogeneous graph neural network
regional aggregation
attention mechanism
spatiotemporal dependencies
url https://www.mdpi.com/2227-7390/13/9/1458
work_keys_str_mv AT xiangtingliu adynamicregionalaggregationbasedheterogeneousgraphneuralnetworkfortrafficprediction
AT chengyuanqian adynamicregionalaggregationbasedheterogeneousgraphneuralnetworkfortrafficprediction
AT xueyangzhao adynamicregionalaggregationbasedheterogeneousgraphneuralnetworkfortrafficprediction
AT xiangtingliu dynamicregionalaggregationbasedheterogeneousgraphneuralnetworkfortrafficprediction
AT chengyuanqian dynamicregionalaggregationbasedheterogeneousgraphneuralnetworkfortrafficprediction
AT xueyangzhao dynamicregionalaggregationbasedheterogeneousgraphneuralnetworkfortrafficprediction